{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:HYXCKNACDAHJD3KYJPJR2DPADC","short_pith_number":"pith:HYXCKNAC","schema_version":"1.0","canonical_sha256":"3e2e253402180e91ed584bd31d0de018967df21a2bc4703b03b3d93ee88b0467","source":{"kind":"arxiv","id":"2012.15840","version":3},"attestation_state":"computed","paper":{"title":"Rethinking Semantic Segmentation from a Sequence-to-Sequence Perspective with Transformers","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Hengshuang Zhao, Jiachen Lu, Jianfeng Feng, Li Zhang, Philip H.S. Torr, Sixiao Zheng, Tao Xiang, Xiatian Zhu, Yabiao Wang, Yanwei Fu, Zekun Luo","submitted_at":"2020-12-31T18:55:57Z","abstract_excerpt":"Most recent semantic segmentation methods adopt a fully-convolutional network (FCN) with an encoder-decoder architecture. The encoder progressively reduces the spatial resolution and learns more abstract/semantic visual concepts with larger receptive fields. Since context modeling is critical for segmentation, the latest efforts have been focused on increasing the receptive field, through either dilated/atrous convolutions or inserting attention modules. However, the encoder-decoder based FCN architecture remains unchanged. In this paper, we aim to provide an alternative perspective by treatin"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2012.15840","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2020-12-31T18:55:57Z","cross_cats_sorted":[],"title_canon_sha256":"f0c2807cb2b87b370e44e9a1c1e5adf69e58893032de95c86029397f29b2db3d","abstract_canon_sha256":"b46e0b0385acda30940a49069f3ccf85638a60b8ba54d9e92d226c8238762987"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:00:29.697763Z","signature_b64":"2jwHNQNS6n9bJHMaxVKIhzuE6m7SDvIkgs3Dqv0GsZI/kJ+uDqmt1jIUZ1nRKsXSbLhby0pWH9SU7s0NVMr1Cw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3e2e253402180e91ed584bd31d0de018967df21a2bc4703b03b3d93ee88b0467","last_reissued_at":"2026-07-05T03:00:29.697377Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:00:29.697377Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Rethinking Semantic Segmentation from a Sequence-to-Sequence Perspective with Transformers","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Hengshuang Zhao, Jiachen Lu, Jianfeng Feng, Li Zhang, Philip H.S. Torr, Sixiao Zheng, Tao Xiang, Xiatian Zhu, Yabiao Wang, Yanwei Fu, Zekun Luo","submitted_at":"2020-12-31T18:55:57Z","abstract_excerpt":"Most recent semantic segmentation methods adopt a fully-convolutional network (FCN) with an encoder-decoder architecture. The encoder progressively reduces the spatial resolution and learns more abstract/semantic visual concepts with larger receptive fields. Since context modeling is critical for segmentation, the latest efforts have been focused on increasing the receptive field, through either dilated/atrous convolutions or inserting attention modules. However, the encoder-decoder based FCN architecture remains unchanged. In this paper, we aim to provide an alternative perspective by treatin"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2012.15840","kind":"arxiv","version":3},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2012.15840/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2012.15840","created_at":"2026-07-05T03:00:29.697433+00:00"},{"alias_kind":"arxiv_version","alias_value":"2012.15840v3","created_at":"2026-07-05T03:00:29.697433+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2012.15840","created_at":"2026-07-05T03:00:29.697433+00:00"},{"alias_kind":"pith_short_12","alias_value":"HYXCKNACDAHJ","created_at":"2026-07-05T03:00:29.697433+00:00"},{"alias_kind":"pith_short_16","alias_value":"HYXCKNACDAHJD3KY","created_at":"2026-07-05T03:00:29.697433+00:00"},{"alias_kind":"pith_short_8","alias_value":"HYXCKNAC","created_at":"2026-07-05T03:00:29.697433+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.22892","citing_title":"IViT: A Novel Interpretable Visual Transformer for Skin Disease Detection","ref_index":38,"is_internal_anchor":false},{"citing_arxiv_id":"2103.14030","citing_title":"Swin Transformer: Hierarchical Vision Transformer using Shifted Windows","ref_index":81,"is_internal_anchor":false},{"citing_arxiv_id":"2106.08254","citing_title":"BEiT: BERT Pre-Training of Image Transformers","ref_index":22,"is_internal_anchor":false},{"citing_arxiv_id":"2102.04306","citing_title":"TransUNet: Transformers Make Strong Encoders for Medical Image Segmentation","ref_index":18,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/HYXCKNACDAHJD3KYJPJR2DPADC","json":"https://pith.science/pith/HYXCKNACDAHJD3KYJPJR2DPADC.json","graph_json":"https://pith.science/api/pith-number/HYXCKNACDAHJD3KYJPJR2DPADC/graph.json","events_json":"https://pith.science/api/pith-number/HYXCKNACDAHJD3KYJPJR2DPADC/events.json","paper":"https://pith.science/paper/HYXCKNAC"},"agent_actions":{"view_html":"https://pith.science/pith/HYXCKNACDAHJD3KYJPJR2DPADC","download_json":"https://pith.science/pith/HYXCKNACDAHJD3KYJPJR2DPADC.json","view_paper":"https://pith.science/paper/HYXCKNAC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2012.15840&json=true","fetch_graph":"https://pith.science/api/pith-number/HYXCKNACDAHJD3KYJPJR2DPADC/graph.json","fetch_events":"https://pith.science/api/pith-number/HYXCKNACDAHJD3KYJPJR2DPADC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HYXCKNACDAHJD3KYJPJR2DPADC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HYXCKNACDAHJD3KYJPJR2DPADC/action/storage_attestation","attest_author":"https://pith.science/pith/HYXCKNACDAHJD3KYJPJR2DPADC/action/author_attestation","sign_citation":"https://pith.science/pith/HYXCKNACDAHJD3KYJPJR2DPADC/action/citation_signature","submit_replication":"https://pith.science/pith/HYXCKNACDAHJD3KYJPJR2DPADC/action/replication_record"}},"created_at":"2026-07-05T03:00:29.697433+00:00","updated_at":"2026-07-05T03:00:29.697433+00:00"}